Article Preview
Top1. Introduction
Nowadays, with the rapid development of the Internet, the era of big data is coming. As the essential development of Internet application, sociality is no longer limited to the transmission of information. It has been the integration of communication and business transaction applications. WeChat is one of the most popular social networks today, which has a lot of advantages. For instance, on the one hand, users can publish messages at anytime and anywhere, and on the other hand, the interaction is becoming strong and easy to operate for users, etc. According to the 40th China Internet development statistics report of CNNIC (China Internet Network Information Center) in June 2017, the usage rate of WeChat is 84.3%, which has a great advantage compared with other public applications. WeChat subscription is one of the main routes of WeChat's information dissemination. WeChat official latest news shows that the total number of subscriptions is over 5,800,000 and growing on average 15,000 every day. With the rapid development of WeChat subscription, it has a great theoretical and practical significance to evaluate the influence of WeChat's subscription within the same article topic. When an article is pushed by WeChat subscription spreads rapidly in WeChat, it means that a lot of people read, comment and praise. Finally, it will affect the whole public opinion situation. If the content of subscription's article involves rumors and bad information, it will have the adverse impact on society and lead to public opinion panic.
At present, social impact analysis algorithm is mainly applied in micro-blog. However, in the aspect of the dissemination of relations and forms of communication, WeChat and micro-blog have a very noticeable difference. As a media tool, Micro-blog is based primarily on interest relationships which are always weak and mostly one-way communication. Micro-blog's attention is given to the propagation speed and the content of public information. So, dissemination speed and breadth will be faster and wider in micro-blog than in WeChat. As a social tool, WeChat establishes relationships based on social relations. Its relationship quality is firm and the two-way relationship. WeChat's attention is paid to the exchange and interaction between private contents. So, its information dissemination speed is not fast, but its audience digestion rate is very high. Therefore, it is necessary to study the spread influence algorithm on WeChat subscription’s topics. At present, the impact analysis algorithm of micro-blog mainly refers to the Google Page Rank (Page, 1998) algorithm and improved algorithm (Lamberti, Sanna & Demartini, 2008; Li, Chen, Wang & Zhang 2011). HITS (Kleinberg, 1999) improved algorithm (Asano, Yu & Nishizeki, 2007; Liu & Lin, 2007) draws on the idea of Page Rank algorithm. Tunke lang constructs a link directed graph and proposes the Twitter Rank algorithm (Weng, Lim, Jiang & He, 2010). The algorithm is mainly to measure the impact of users on a topic. The main idea is that given a topic which the user's influence is meant by the influence of all his fans (Yang, Kefei, Shiren, Yan, Ding, & Yang, 2012). However, the algorithm only considers the interaction between users with similar topics and is also not applicable to the WeChat subscription's article dissemination characteristics. Because the WeChat subscription's information dissemination characteristics have the driving frequency flexibility and the posting time is not a fixed characteristic, it makes subscription's graphics and text push more ‘casual’ but not ‘arbitrary’. Users have their own reading habits, so it is necessary to analyze the relationship between the WeChat subscription posting time and the subscription influence. In WeChat research field, the document (Liao, Shi, Chi & Cheng, 2017) made a detailed review of literature on blended learning and WeChat. Other researchers (Qiu, Li, Chen, Chen, Chen & Chen, 2017) analyze the daily usage logs from WeChat group messaging platform with the goal of understanding the processes by which social messaging groups come together, grow new members, and evolve over time. The document (Mao, Liu, Zhang & Ma, 2014) analyzed the user's influence by using the time and quantity of micro-blog released by micro-blog users, but this method did not introduce the actual topic to analyze the impact of users on a social problem. Therefore, this paper proposes a WeChat subscription topic influence model based on WeChat subscription's own specific communication ability, time characteristics and communication capacity numerical characteristics. So that it can truly and effectively reflect the WeChat subscription articles' topic spread of influence.